Remote service interruption via non-finite temperature
Published Jun 22, 2026 · Updated Jun 22, 2026
Improper temperature validation in vLLM before 0.23.1rc0 allows remote attackers to crash an inference worker via API requests. SamplingParams._verify_args compares the caller-supplied temperature with numeric bounds but never rejects NaN or positive infinity, so both values reach GPU sampling kernels. A network client able to submit generation requests can interrupt concurrent inference by triggering undefined GPU behavior or a CUDA error; no data disclosure is reported.
Summary
What happened
Improper temperature validation in vLLM before 0.23.1rc0 allows remote attackers to crash an inference worker via API requests. SamplingParams._verify_args compares the caller-supplied temperature with numeric bounds but never rejects NaN or positive infinity, so both values reach GPU sampling kernels. A network client able to submit generation requests can interrupt concurrent inference by triggering undefined GPU behavior or a CUDA error; no data disclosure is reported.
The record
- CVE
- CVE-2026-54235
- Published
- Jun 22, 2026
- Updated
- Jun 22, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-1287, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 22, 2026CVE publishedPublication date reported by the CVE source.
- Jun 22, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.23.1rc0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo